DeVIT sorts quantized vision transformer weights into a differential chain and reuses the input-by-smallest-weight product, converting most weight multiplications into shift-add operations.
Stream-ViT: learning streamlined convolutions in vision transformer,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DeVIT: Low-Power Vision Transformer Acceleration Using Delta Computation
DeVIT sorts quantized vision transformer weights into a differential chain and reuses the input-by-smallest-weight product, converting most weight multiplications into shift-add operations.